{
  "id": 10111,
  "title": "Required model documentation and code",
  "url": "/competitions/seizure-detection/writeups/michael-hills-required-model-documentation-and-cod",
  "author_name": "",
  "post_date": "2014-08-25T21:23:43.763Z",
  "votes": 25,
  "comment_count": 8,
  "views": 8820,
  "content": "<p>Hey everyone,</p>\n<p>My code and documentation are now ready. It was&nbsp;great fun competing with you all,&nbsp;that final week was pretty intense!</p>\n<p>https://github.com/MichaelHills/seizure-detection/raw/master/seizure-detection.pdf</p>\n<p>https://github.com/MichaelHills/seizure-detection</p>\n<p>Quickly summarising my model, for feature selection I used FFT 1-47Hz, concatenated with correlation coefficients (and their eigenvalues) of both the FFT output data, as well as the input time data. The data was then trained on per-patient Random Forest classifiers (3000 trees).</p>",
  "messages": [
    {
      "id": "52439",
      "postDate": "08/25/2014 21:23:43",
      "content": "<p>Hey everyone,</p>\n<p>My code and documentation are now ready. It was&nbsp;great fun competing with you all,&nbsp;that final week was pretty intense!</p>\n<p>https://github.com/MichaelHills/seizure-detection/raw/master/seizure-detection.pdf</p>\n<p>https://github.com/MichaelHills/seizure-detection</p>\n<p>Quickly summarising my model, for feature selection I used FFT 1-47Hz, concatenated with correlation coefficients (and their eigenvalues) of both the FFT output data, as well as the input time data. The data was then trained on per-patient Random Forest classifiers (3000 trees).</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52474",
      "postDate": "08/26/2014 18:58:22",
      "content": "<p>Congrats for winning the contest! and thanks for your well-structured solution file.&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "52506",
      "postDate": "08/27/2014 13:33:00",
      "content": "<p>Bravo!</p>\n<p>Compliments!</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "53258",
      "postDate": "09/06/2014 19:19:53",
      "content": "<p>Hi all,</p>\n<p>Our model description and code are available on github at https://github.com/asood314/SeizureDetection.&nbsp; </p>\n<p>Thanks to everyone here at kaggle,</p>\n<p>Team cdipsters.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "53266",
      "postDate": "09/07/2014 00:49:53",
      "content": "<p>Code and documentation for team Olson and Mingle is up&nbsp;at&nbsp;<a href=\"https://github.com/ebenolson/seizure-detection\">https://github.com/ebenolson/seizure-detection</a></p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "53480",
      "postDate": "09/11/2014 04:18:30",
      "content": "<p>Awesome! Congrats everyone! 200 teams, wow!</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "57625",
      "postDate": "11/10/2014 17:43:48",
      "content": "<p>I have a quick question. First you did an fft on the dataset. What was the outcome of this? Did you have 48 variables (from 1-48 hz)? If that&#8217;s the case, did you have to average the frequency of each Hz?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "86410",
      "postDate": "07/22/2015 02:45:53",
      "content": "<p>Thanks, very useful for the new EEG challenge :)</p>",
      "rawMarkdown": "Thanks, very useful for the new EEG challenge :)",
      "votes": null
    },
    {
      "id": "950519",
      "postDate": "07/29/2020 12:52:16",
      "content": "<p>This is great</p>",
      "rawMarkdown": "This is great",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 52474,
      "author_name": "mojtaba",
      "author_url": "",
      "post_date": "08/26/2014 18:58:22",
      "content": "<p>Congrats for winning the contest! and thanks for your well-structured solution file.&nbsp;</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 52506,
      "author_name": "vadymgnatkovsky",
      "author_url": "",
      "post_date": "08/27/2014 13:33:00",
      "content": "<p>Bravo!</p>\n<p>Compliments!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 53258,
      "author_name": "ishan4",
      "author_url": "",
      "post_date": "09/06/2014 19:19:53",
      "content": "<p>Hi all,</p>\n<p>Our model description and code are available on github at https://github.com/asood314/SeizureDetection.&nbsp; </p>\n<p>Thanks to everyone here at kaggle,</p>\n<p>Team cdipsters.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 53266,
      "author_name": "emolson",
      "author_url": "",
      "post_date": "09/07/2014 00:49:53",
      "content": "<p>Code and documentation for team Olson and Mingle is up&nbsp;at&nbsp;<a href=\"https://github.com/ebenolson/seizure-detection\">https://github.com/ebenolson/seizure-detection</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 53480,
      "author_name": "amyrobinson",
      "author_url": "",
      "post_date": "09/11/2014 04:18:30",
      "content": "<p>Awesome! Congrats everyone! 200 teams, wow!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 57625,
      "author_name": "mahi83",
      "author_url": "",
      "post_date": "11/10/2014 17:43:48",
      "content": "<p>I have a quick question. First you did an fft on the dataset. What was the outcome of this? Did you have 48 variables (from 1-48 hz)? If that&#8217;s the case, did you have to average the frequency of each Hz?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 86410,
      "author_name": "pierregutierrez",
      "author_url": "",
      "post_date": "07/22/2015 02:45:53",
      "content": "<p>Thanks, very useful for the new EEG challenge :)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 950519,
      "author_name": "shobhitgupta8005",
      "author_url": "",
      "post_date": "07/29/2020 12:52:16",
      "content": "<p>This is great</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "52439": "",
    "52474": "",
    "52506": "",
    "53258": "",
    "53266": "",
    "53480": "",
    "57625": "",
    "86410": "Thanks, very useful for the new EEG challenge :)",
    "950519": "This is great"
  },
  "source": "meta"
}